Challenges in Visual Anomaly Detection for Mobile Robots

TL;DR

This paper addresses visual anomaly detection in mobile robots, introducing a new dataset and evaluating unsupervised deep learning methods for improved real-world deployment.

Contribution

It presents a novel dataset for visual anomaly detection in mobile robots and assesses state-of-the-art unsupervised deep learning approaches.

Findings

New dataset tailored for mobile robot anomaly detection

Evaluation of unsupervised deep learning methods on the dataset

Discussion on deployment challenges in real scenarios

Abstract

We consider the task of detecting anomalies for autonomous mobile robots based on vision. We categorize relevant types of visual anomalies and discuss how they can be detected by unsupervised deep learning methods. We propose a novel dataset built specifically for this task, on which we test a state-of-the-art approach; we finally discuss deployment in a real scenario.